Code
library(tidyverse)
library(here)
library(dplyr)
library(broom)
library(DT)
library(knitr)
library(kableExtra)Challenge 9
Code
names <- read_csv(file = here("Week9", "Lab9", "StateNames_A.csv"))
DT::datatable(names)1
Code
names |>
group_by(State, Gender) |>
filter(Name == "Allison") |>
summarize(Total = sum(Count)) |>
kable(format = "html",
caption = "Number of babies Named 'Allison' by State") |>
kable_material(c("striped", "hover"))| State | Gender | Total |
|---|---|---|
| AK | F | 232 |
| AL | F | 1535 |
| AR | F | 1198 |
| AZ | F | 1880 |
| CA | F | 12413 |
| CO | F | 1594 |
| CT | F | 1099 |
| DC | F | 321 |
| DE | F | 294 |
| FL | F | 4455 |
| GA | F | 3257 |
| HI | F | 183 |
| IA | F | 1477 |
| ID | F | 451 |
| IL | F | 5110 |
| IN | F | 3067 |
| KS | F | 1283 |
| KY | F | 1905 |
| KY | M | 20 |
| LA | F | 1209 |
| MA | F | 2218 |
| MD | F | 2229 |
| ME | F | 340 |
| MI | F | 4014 |
| MN | F | 2374 |
| MO | F | 2882 |
| MS | F | 817 |
| MT | F | 226 |
| NC | F | 3435 |
| ND | F | 285 |
| NE | F | 807 |
| NH | F | 412 |
| NJ | F | 3052 |
| NM | F | 399 |
| NV | F | 729 |
| NY | F | 5747 |
| OH | F | 5487 |
| OK | F | 1421 |
| OR | F | 1186 |
| PA | F | 4307 |
| RI | F | 306 |
| SC | F | 1228 |
| SD | F | 376 |
| TN | F | 2488 |
| TX | F | 10192 |
| UT | F | 1125 |
| VA | F | 3220 |
| VT | F | 135 |
| WA | F | 1956 |
| WI | F | 2367 |
| WV | F | 813 |
| WY | F | 142 |
2
Code
allison_f <- names |>
group_by(Year) |>
filter(Name == "Allison", Gender == "F") |>
summarize(Total = sum(Count))3
Code
allison_f |>
ggplot(mapping = aes(x = Year, y = Total)) +
geom_col() +
lims(x = c(1996, 2014)) +
labs(x = "Year", y = "",
title = "Number of Children Named 'Allison' per Year in the US")
4
Code
linear_model <- lm(Total ~ Year, data = allison_f)
broom::tidy(linear_model) |>
kable(format = "html") |>
kable_material(c("striped", "hover"))| term | estimate | std.error | statistic | p.value |
|---|---|---|---|---|
| (Intercept) | 209689.7609 | 42971.50497 | 4.879740 | 0.0001669 |
| Year | -101.5191 | 21.42676 | -4.737959 | 0.0002228 |
5
y = 209689.7609 - 101.5191(x)
6
Code
linear_model |>
broom::augment() |>
ggplot(mapping = aes(y = .resid, x = .fitted)) +
geom_point() +
stat_smooth(method = "lm")
7
The resulting linear model doesn’t provide enough information to determine the trend over time.
8
Code
names |>
group_by(Name, Year) |>
filter(Name == "Allan" | Name == "Allen" | Name == "Alan") |>
summarize(Total = sum(Count)) |>
ggplot(mapping = aes(x = Year, y = Total, fill = Name, color = Name)) +
geom_col() +
lims(x = c(1996, 2014))
9
Code
names |>
filter(Name == "Allan" | Name == "Allen" | Name == "Alan", Year == 2000,
State == "PA" | State == "CA") |>
group_by(Name, State) |>
summarize(Count = sum(Count)) |>
pivot_wider(names_from = Name, values_from = Count) |>
kable(format = "html", col.names = c('State', 'Alans', 'Allans', 'Allens'),
caption = "Number of Babies Named a Variation of 'Allan' in CA & PA") |>
kable_material(c("striped", "hover"))| State | Alans | Allans | Allens |
|---|---|---|---|
| CA | 584 | 131 | 176 |
| PA | 51 | 12 | 56 |
10
Code
names |>
filter(Name == "Allan" | Name == "Allen" | Name == "Alan", Year == 2000,
State == "PA" | State == "CA") |>
group_by(State) |>
count(Name, wt = Count) |>
mutate(prop = n / sum(n)) |>
select(-n) |>
pivot_wider(names_from = Name, values_from = prop) |>
kable(format = "html", col.names = c('State', 'Alan', 'Allan', 'Allen'),
caption = "Proportion of Babies Named a Variation of 'Allan' in CA & PA") |>
kable_material(c("striped", "hover"))| State | Alan | Allan | Allen |
|---|---|---|---|
| CA | 0.6554433 | 0.1470258 | 0.1975309 |
| PA | 0.4285714 | 0.1008403 | 0.4705882 |